Join

这是数据库操作join的特例，目的是讲file1和file2做join操作

file1如下：

1 jack
2 daniel
4 martin
5 king
3 mary
4 jane

file2如下：

5 london
2 london
4 rome
2 gasgow
3 paris
1 madnd

要求的结果如下：

1    jack:madnd
2    daniel:london
2    daniel:gasgow
3    mary:paris
4    martin:rome
4    jane:rome
5    king:london

举个简单例子

file1   1 cjd                                                                1  0cjd

file2    1 shanghai                         map之后得到  1 1shanghai                 reduce之后得到     1 cjd：shanghai

            1 hangzhou                                                   1 1hangzhou                                                  1 cjd:hangzhou

代码如下：

import java.io.IOException;
import java.util.List;
import java.util.ArrayList;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;

public class Join extends Configured implements Tool{

	enum Counter
	{
		LINERSKIP;
	}
	
	
	public static class MapOne extends Mapper<LongWritable,Text,Text,Text> 
	{
		public void map(LongWritable key,Text value,Context context) throws IOException,InterruptedException
		{
			try{
				String tag = "0";
				String[] linesplit = value.toString().split(" ");
				context.write(new Text(linesplit[0]), new Text(tag+linesplit[1]));		
			}
			catch(java.lang.ArrayIndexOutOfBoundsException e){
				context.getCounter(Counter.LINERSKIP).increment(1);
				return;
			}
		}
		
	}
	public static class MapTwo extends Mapper<LongWritable,Text,Text,Text> 
	{
		public void map(LongWritable key,Text value,Context context) throws IOException,InterruptedException
		{
			try{
				String tag = "1";
				String[] linesplit = value.toString().split(" ");
				context.write(new Text(linesplit[0]), new Text(tag+linesplit[1]));
			}
			catch(java.lang.ArrayIndexOutOfBoundsException e){
				context.getCounter(Counter.LINERSKIP).increment(1);
				return;
			}
		}
	}

	public static class Reduce extends Reducer<Text,Text,Text,Text>
	{
		public void reduce(Text key , Iterable<Text> values,Context context) throws IOException,InterruptedException
		{
			List<String> list0 = new ArrayList<String>();
			List<String> list1 = new ArrayList<String>();
			for(Text value : values)
			{
				String str = value.toString();
				if(str.charAt(0) == '0'){
					list0.add(str.substring(1));
				}
				else{
					list1.add(str.substring(1));
				}
			}
		    for(String str0 : list0)
		    	for(String str1 : list1)
		    	{
		    		String valueinfo = str0 + ":" + str1;
		    		context.write(key, new Text(valueinfo) );
		    	}
		}
	}

	public int run(String[] args)throws Exception
	{
		Configuration conf = getConf();
		Job job = new Job(conf,"Join");
		
		job.setJarByClass(Join.class);
		
		MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class,MapOne.class);//两个map对应两个输入文件
		MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class,MapTwo.class);
		FileOutputFormat.setOutputPath(job,new Path(args[2]));
		job.setReducerClass(Reduce.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		job.waitForCompletion(true);
		return job.isSuccessful() ? 0 : 1;
	}
	
	public static void main(String[] args) throws Exception
	{
		int res = ToolRunner.run(new Configuration(), new Join(),args);
		System.exit(res);
	}

}